相关论文: Dynamics Based Neural Encoding with Inter-Intra Re…

Standard video codecs rely on optical flow to guide inter-frame prediction: pixels from reference frames are moved via motion vectors to predict target video frames. We propose to learn binary motion codes that are encoded based on an input…

Psychovisual models suggest human vision decouples low-level feature extraction from higher cognition by first forming intermediate abstractions. In contrast, deep learning-based vision models routinely extract and aggregate features using…

A major goal of neuroscience is to understand brain computations during visual processing in naturalistic settings. A dominant approach is to use image-computable deep neural networks trained with different task objectives as a basis for…

Existing approaches to modeling associations between visual stimuli and brain responses are facing difficulties in handling between-subject variance and model generalization. Inspired by the recent progress in modeling speech-brain…

Encoding a sequence of observations is an essential task with many applications. The encoding can become highly efficient when the observations are generated by a dynamical system. A dynamical system imposes regularities on the observations…

A number of techniques for interpretability have been presented for deep learning in computer vision, typically with the goal of understanding what the networks have based their classification on. However, interpretability for deep video…

Encoding models that predict brain response patterns to stimuli are one way to capture this relationship between variability in bottom-up neural systems and individual's behavior or pathological state. However, they generally need a large…

Recent advances in neuroimaging along with algorithmic innovations in statistical learning from network data offer a unique pathway to integrate brain structure and function, and thus facilitate revealing some of the brain's organizing…

Dynamic imaging is a recently proposed action description paradigm for simultaneously capturing motion and temporal evolution information, particularly in the context of deep convolutional neural networks (CNNs). Compared with optical flow…

While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular, 3D context has been shown to be an extremely important cue…

Automatic 3D neuron reconstruction is critical for analysing the morphology and functionality of neurons in brain circuit activities. However, the performance of existing tracing algorithms is hinged by the low image quality. Recently, a…

While deep learning surpasses human-level performance in narrow and specific vision tasks, it is fragile and over-confident in classification. For example, minor transformations in perspective, illumination, or object deformation in the…

Decoding visual representations from brain signals has attracted significant attention in both neuroscience and artificial intelligence. However, the degree to which brain signals truly encode visual information remains unclear. Current…

Interpretability of deep neural networks (DNNs) is essential since it enables users to understand the overall strengths and weaknesses of the models, conveys an understanding of how the models will behave in the future, and how to diagnose…

Convolutional neural networks (CNNs) have been extensively applied for image recognition problems giving state-of-the-art results on recognition, detection, segmentation and retrieval. In this work we propose and evaluate several deep…

Recently, deep image compression has shown a big progress in terms of coding efficiency and image quality improvement. However, relatively less attention has been put on video compression using deep learning networks. In the paper, we first…

Implicit neural representations (INR) have gained increasing attention in representing 3D scenes and images, and have been recently applied to encode videos (e.g., NeRV, E-NeRV). While achieving promising results, existing INR-based methods…

We developed a tool for visualizing and analyzing large pre-trained vision models by mapping them onto the brain, thus exposing their hidden inside. Our innovation arises from a surprising usage of brain encoding: predicting brain fMRI…

Deep learning methods have achieved impressive performance for multi-class medical image segmentation. However, they are limited in their ability to encode topological interactions among different classes (e.g., containment and exclusion).…

Encoding and decoding models are widely used in systems, cognitive, and computational neuroscience to make sense of brain-activity data. However, the interpretation of their results requires care. Decoding models can help reveal whether…